Single-pixel 3D imaging based on fusion temporal data of single photon detector and millimeter-wave radar

TL;DR

This paper introduces a novel 3D imaging approach combining single-photon detection and millimeter-wave radar data, using neural networks to enhance image quality and eliminate symmetry blur in reconstructed scenes.

Contribution

It presents a fusion data method that integrates single-photon and radar temporal data for 3D imaging, overcoming symmetry blur issues with neural network reconstruction.

Findings

Fusion method effectively eliminates symmetry blur.

Improves 3D image reconstruction quality.

Validated through simulation and experiments.

Abstract

Recently, there has been increased attention towards 3D imaging using single-pixel single-photon detection (also known as temporal data) due to its potential advantages in terms of cost and power efficiency. However, to eliminate the symmetry blur in the reconstructed images, a fixed background is required. This paper proposes a fusion-data-based 3D imaging method that utilizes a single-pixel single-photon detector and a millimeter-wave radar to capture temporal histograms of a scene from multiple perspectives. Subsequently, the 3D information can be reconstructed from the one-dimensional fusion temporal data by using Artificial Neural Network (ANN). Both the simulation and experimental results demonstrate that our fusion method effectively eliminates symmetry blur and improves the quality of the reconstructed images.